Accelerating Reinforcement Learning through GPU Atari Emulation.
Steven DaltonIuri FrosioPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- linear value function approximation
- function approximation
- state space
- reinforcement learning algorithms
- control problems
- markov decision problems
- learning algorithm
- model free
- temporal difference
- markov games
- markov decision processes
- reinforcement learning methods
- optimal policy
- action selection
- partially observable
- optimal control
- graphics processing units
- dynamic programming